This paper presents a pioneering effort to involve machine in checking document authenticity. A particular class of security documents has been considered for the present experiment. Bank cheques, several kinds of tickets like lottery tickets, air tickets, etc., legal deeds, certificates, mark sheets, postal stamps, etc. all these documents fall under the same class as far as security is concerned. Criminals' efforts for generating fraudulent version of such documents are on the rise. This study attempts to develop a general framework for automatic authenticity verification of such security documents. The proposed method first computationally extracts the security features from the document images and then the notion of authenticity vs. duplicity is defined in the feature space. Bank cheques are taken as a reference for conducting experiment. Support Vector Machines (SVMs) are used to verify authenticity of these cheques. Non-linear kernel functions are used to conduct this experiment. Results show that a polynomial kernel based SVM gives about 99.5% accuracy discriminating duplicate cheques from genuine ones. This strongly attests the viability of the proposed approach for machine authentication of printed security documents.

An image analysis based pattern classification method is proposed to authentic the printing process used in printing different texts on currency notes. Features suitable for doing this are selected and then studied to detect fraudulent samples based on the printing method. This classification is done by using Support Vector Machines and Neural Nets. The discriminatory power of the selected features in authenticating the printing process is tested using the Linear Discriminate Analysis. Experimental results show that the proposed framework provides a highly accurate framework for authenticating the printing process in bank notes.

No abstract

No abstract

No abstract